diff options
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/acpi/nfit/core.c | 679 | ||||
-rw-r--r-- | drivers/acpi/nfit/mce.c | 5 | ||||
-rw-r--r-- | drivers/acpi/nfit/nfit.h | 22 | ||||
-rw-r--r-- | drivers/dax/device.c | 38 | ||||
-rw-r--r-- | drivers/dax/pmem.c | 18 | ||||
-rw-r--r-- | drivers/nvdimm/Kconfig | 11 | ||||
-rw-r--r-- | drivers/nvdimm/Makefile | 1 | ||||
-rw-r--r-- | drivers/nvdimm/btt_devs.c | 21 | ||||
-rw-r--r-- | drivers/nvdimm/bus.c | 14 | ||||
-rw-r--r-- | drivers/nvdimm/claim.c | 2 | ||||
-rw-r--r-- | drivers/nvdimm/core.c | 6 | ||||
-rw-r--r-- | drivers/nvdimm/dax_devs.c | 5 | ||||
-rw-r--r-- | drivers/nvdimm/dimm.c | 8 | ||||
-rw-r--r-- | drivers/nvdimm/dimm_devs.c | 7 | ||||
-rw-r--r-- | drivers/nvdimm/label.c | 85 | ||||
-rw-r--r-- | drivers/nvdimm/label.h | 2 | ||||
-rw-r--r-- | drivers/nvdimm/namespace_devs.c | 42 | ||||
-rw-r--r-- | drivers/nvdimm/nd.h | 1 | ||||
-rw-r--r-- | drivers/nvdimm/of_pmem.c | 119 | ||||
-rw-r--r-- | drivers/nvdimm/pfn_devs.c | 25 | ||||
-rw-r--r-- | drivers/nvdimm/pmem.c | 14 | ||||
-rw-r--r-- | drivers/nvdimm/region.c | 4 | ||||
-rw-r--r-- | drivers/nvdimm/region_devs.c | 9 |
23 files changed, 613 insertions, 525 deletions
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index eb09ef55c38a..dbe43503cba5 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -35,16 +35,6 @@ static bool force_enable_dimms; module_param(force_enable_dimms, bool, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(force_enable_dimms, "Ignore _STA (ACPI DIMM device) status"); -static unsigned int scrub_timeout = NFIT_ARS_TIMEOUT; -module_param(scrub_timeout, uint, S_IRUGO|S_IWUSR); -MODULE_PARM_DESC(scrub_timeout, "Initial scrub timeout in seconds"); - -/* after three payloads of overflow, it's dead jim */ -static unsigned int scrub_overflow_abort = 3; -module_param(scrub_overflow_abort, uint, S_IRUGO|S_IWUSR); -MODULE_PARM_DESC(scrub_overflow_abort, - "Number of times we overflow ARS results before abort"); - static bool disable_vendor_specific; module_param(disable_vendor_specific, bool, S_IRUGO); MODULE_PARM_DESC(disable_vendor_specific, @@ -59,6 +49,10 @@ module_param(default_dsm_family, int, S_IRUGO); MODULE_PARM_DESC(default_dsm_family, "Try this DSM type first when identifying NVDIMM family"); +static bool no_init_ars; +module_param(no_init_ars, bool, 0644); +MODULE_PARM_DESC(no_init_ars, "Skip ARS run at nfit init time"); + LIST_HEAD(acpi_descs); DEFINE_MUTEX(acpi_desc_lock); @@ -196,7 +190,7 @@ static int xlat_nvdimm_status(struct nvdimm *nvdimm, void *buf, unsigned int cmd * In the _LSI, _LSR, _LSW case the locked status is * communicated via the read/write commands */ - if (nfit_mem->has_lsi) + if (nfit_mem->has_lsr) break; if (status >> 16 & ND_CONFIG_LOCKED) @@ -476,14 +470,14 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, in_buf.buffer.length = call_pkg->nd_size_in; } - dev_dbg(dev, "%s:%s cmd: %d: func: %d input length: %d\n", - __func__, dimm_name, cmd, func, in_buf.buffer.length); + dev_dbg(dev, "%s cmd: %d: func: %d input length: %d\n", + dimm_name, cmd, func, in_buf.buffer.length); print_hex_dump_debug("nvdimm in ", DUMP_PREFIX_OFFSET, 4, 4, in_buf.buffer.pointer, min_t(u32, 256, in_buf.buffer.length), true); /* call the BIOS, prefer the named methods over _DSM if available */ - if (nvdimm && cmd == ND_CMD_GET_CONFIG_SIZE && nfit_mem->has_lsi) + if (nvdimm && cmd == ND_CMD_GET_CONFIG_SIZE && nfit_mem->has_lsr) out_obj = acpi_label_info(handle); else if (nvdimm && cmd == ND_CMD_GET_CONFIG_DATA && nfit_mem->has_lsr) { struct nd_cmd_get_config_data_hdr *p = buf; @@ -506,8 +500,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, } if (!out_obj) { - dev_dbg(dev, "%s:%s _DSM failed cmd: %s\n", __func__, dimm_name, - cmd_name); + dev_dbg(dev, "%s _DSM failed cmd: %s\n", dimm_name, cmd_name); return -EINVAL; } @@ -528,13 +521,13 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, } if (out_obj->package.type != ACPI_TYPE_BUFFER) { - dev_dbg(dev, "%s:%s unexpected output object type cmd: %s type: %d\n", - __func__, dimm_name, cmd_name, out_obj->type); + dev_dbg(dev, "%s unexpected output object type cmd: %s type: %d\n", + dimm_name, cmd_name, out_obj->type); rc = -EINVAL; goto out; } - dev_dbg(dev, "%s:%s cmd: %s output length: %d\n", __func__, dimm_name, + dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name, cmd_name, out_obj->buffer.length); print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4, out_obj->buffer.pointer, @@ -546,14 +539,14 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, out_obj->buffer.length - offset); if (offset + out_size > out_obj->buffer.length) { - dev_dbg(dev, "%s:%s output object underflow cmd: %s field: %d\n", - __func__, dimm_name, cmd_name, i); + dev_dbg(dev, "%s output object underflow cmd: %s field: %d\n", + dimm_name, cmd_name, i); break; } if (in_buf.buffer.length + offset + out_size > buf_len) { - dev_dbg(dev, "%s:%s output overrun cmd: %s field: %d\n", - __func__, dimm_name, cmd_name, i); + dev_dbg(dev, "%s output overrun cmd: %s field: %d\n", + dimm_name, cmd_name, i); rc = -ENXIO; goto out; } @@ -655,7 +648,7 @@ static bool add_spa(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_spa->list); memcpy(nfit_spa->spa, spa, sizeof(*spa)); list_add_tail(&nfit_spa->list, &acpi_desc->spas); - dev_dbg(dev, "%s: spa index: %d type: %s\n", __func__, + dev_dbg(dev, "spa index: %d type: %s\n", spa->range_index, spa_type_name(nfit_spa_type(spa))); return true; @@ -684,8 +677,8 @@ static bool add_memdev(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_memdev->list); memcpy(nfit_memdev->memdev, memdev, sizeof(*memdev)); list_add_tail(&nfit_memdev->list, &acpi_desc->memdevs); - dev_dbg(dev, "%s: memdev handle: %#x spa: %d dcr: %d flags: %#x\n", - __func__, memdev->device_handle, memdev->range_index, + dev_dbg(dev, "memdev handle: %#x spa: %d dcr: %d flags: %#x\n", + memdev->device_handle, memdev->range_index, memdev->region_index, memdev->flags); return true; } @@ -727,7 +720,7 @@ static bool add_dcr(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_dcr->list); memcpy(nfit_dcr->dcr, dcr, sizeof_dcr(dcr)); list_add_tail(&nfit_dcr->list, &acpi_desc->dcrs); - dev_dbg(dev, "%s: dcr index: %d windows: %d\n", __func__, + dev_dbg(dev, "dcr index: %d windows: %d\n", dcr->region_index, dcr->windows); return true; } @@ -754,7 +747,7 @@ static bool add_bdw(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_bdw->list); memcpy(nfit_bdw->bdw, bdw, sizeof(*bdw)); list_add_tail(&nfit_bdw->list, &acpi_desc->bdws); - dev_dbg(dev, "%s: bdw dcr: %d windows: %d\n", __func__, + dev_dbg(dev, "bdw dcr: %d windows: %d\n", bdw->region_index, bdw->windows); return true; } @@ -793,7 +786,7 @@ static bool add_idt(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_idt->list); memcpy(nfit_idt->idt, idt, sizeof_idt(idt)); list_add_tail(&nfit_idt->list, &acpi_desc->idts); - dev_dbg(dev, "%s: idt index: %d num_lines: %d\n", __func__, + dev_dbg(dev, "idt index: %d num_lines: %d\n", idt->interleave_index, idt->line_count); return true; } @@ -833,7 +826,7 @@ static bool add_flush(struct acpi_nfit_desc *acpi_desc, INIT_LIST_HEAD(&nfit_flush->list); memcpy(nfit_flush->flush, flush, sizeof_flush(flush)); list_add_tail(&nfit_flush->list, &acpi_desc->flushes); - dev_dbg(dev, "%s: nfit_flush handle: %d hint_count: %d\n", __func__, + dev_dbg(dev, "nfit_flush handle: %d hint_count: %d\n", flush->device_handle, flush->hint_count); return true; } @@ -846,7 +839,7 @@ static bool add_platform_cap(struct acpi_nfit_desc *acpi_desc, mask = (1 << (pcap->highest_capability + 1)) - 1; acpi_desc->platform_cap = pcap->capabilities & mask; - dev_dbg(dev, "%s: cap: %#x\n", __func__, acpi_desc->platform_cap); + dev_dbg(dev, "cap: %#x\n", acpi_desc->platform_cap); return true; } @@ -893,7 +886,7 @@ static void *add_table(struct acpi_nfit_desc *acpi_desc, return err; break; case ACPI_NFIT_TYPE_SMBIOS: - dev_dbg(dev, "%s: smbios\n", __func__); + dev_dbg(dev, "smbios\n"); break; case ACPI_NFIT_TYPE_CAPABILITIES: if (!add_platform_cap(acpi_desc, table)) @@ -1250,8 +1243,11 @@ static ssize_t scrub_show(struct device *dev, if (nd_desc) { struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); + mutex_lock(&acpi_desc->init_mutex); rc = sprintf(buf, "%d%s", acpi_desc->scrub_count, - (work_busy(&acpi_desc->work)) ? "+\n" : "\n"); + work_busy(&acpi_desc->dwork.work) + && !acpi_desc->cancel ? "+\n" : "\n"); + mutex_unlock(&acpi_desc->init_mutex); } device_unlock(dev); return rc; @@ -1621,7 +1617,7 @@ void __acpi_nvdimm_notify(struct device *dev, u32 event) struct nfit_mem *nfit_mem; struct acpi_nfit_desc *acpi_desc; - dev_dbg(dev->parent, "%s: %s: event: %d\n", dev_name(dev), __func__, + dev_dbg(dev->parent, "%s: event: %d\n", dev_name(dev), event); if (event != NFIT_NOTIFY_DIMM_HEALTH) { @@ -1654,12 +1650,23 @@ static void acpi_nvdimm_notify(acpi_handle handle, u32 event, void *data) device_unlock(dev->parent); } +static bool acpi_nvdimm_has_method(struct acpi_device *adev, char *method) +{ + acpi_handle handle; + acpi_status status; + + status = acpi_get_handle(adev->handle, method, &handle); + + if (ACPI_SUCCESS(status)) + return true; + return false; +} + static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, u32 device_handle) { struct acpi_device *adev, *adev_dimm; struct device *dev = acpi_desc->dev; - union acpi_object *obj; unsigned long dsm_mask; const guid_t *guid; int i; @@ -1732,25 +1739,15 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, 1ULL << i)) set_bit(i, &nfit_mem->dsm_mask); - obj = acpi_label_info(adev_dimm->handle); - if (obj) { - ACPI_FREE(obj); - nfit_mem->has_lsi = 1; - dev_dbg(dev, "%s: has _LSI\n", dev_name(&adev_dimm->dev)); - } - - obj = acpi_label_read(adev_dimm->handle, 0, 0); - if (obj) { - ACPI_FREE(obj); - nfit_mem->has_lsr = 1; + if (acpi_nvdimm_has_method(adev_dimm, "_LSI") + && acpi_nvdimm_has_method(adev_dimm, "_LSR")) { dev_dbg(dev, "%s: has _LSR\n", dev_name(&adev_dimm->dev)); + nfit_mem->has_lsr = true; } - obj = acpi_label_write(adev_dimm->handle, 0, 0, NULL); - if (obj) { - ACPI_FREE(obj); - nfit_mem->has_lsw = 1; + if (nfit_mem->has_lsr && acpi_nvdimm_has_method(adev_dimm, "_LSW")) { dev_dbg(dev, "%s: has _LSW\n", dev_name(&adev_dimm->dev)); + nfit_mem->has_lsw = true; } return 0; @@ -1839,10 +1836,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) cmd_mask |= nfit_mem->dsm_mask & NVDIMM_STANDARD_CMDMASK; } - if (nfit_mem->has_lsi) + if (nfit_mem->has_lsr) { set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask); - if (nfit_mem->has_lsr) set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask); + } if (nfit_mem->has_lsw) set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask); @@ -2338,7 +2335,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, nvdimm = nd_blk_region_to_dimm(ndbr); nfit_mem = nvdimm_provider_data(nvdimm); if (!nfit_mem || !nfit_mem->dcr || !nfit_mem->bdw) { - dev_dbg(dev, "%s: missing%s%s%s\n", __func__, + dev_dbg(dev, "missing%s%s%s\n", nfit_mem ? "" : " nfit_mem", (nfit_mem && nfit_mem->dcr) ? "" : " dcr", (nfit_mem && nfit_mem->bdw) ? "" : " bdw"); @@ -2357,7 +2354,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address, nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr)); if (!mmio->addr.base) { - dev_dbg(dev, "%s: %s failed to map bdw\n", __func__, + dev_dbg(dev, "%s failed to map bdw\n", nvdimm_name(nvdimm)); return -ENOMEM; } @@ -2368,8 +2365,8 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, rc = nfit_blk_init_interleave(mmio, nfit_mem->idt_bdw, nfit_mem->memdev_bdw->interleave_ways); if (rc) { - dev_dbg(dev, "%s: %s failed to init bdw interleave\n", - __func__, nvdimm_name(nvdimm)); + dev_dbg(dev, "%s failed to init bdw interleave\n", + nvdimm_name(nvdimm)); return rc; } @@ -2380,7 +2377,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, mmio->addr.base = devm_nvdimm_ioremap(dev, nfit_mem->spa_dcr->address, nfit_mem->spa_dcr->length); if (!mmio->addr.base) { - dev_dbg(dev, "%s: %s failed to map dcr\n", __func__, + dev_dbg(dev, "%s failed to map dcr\n", nvdimm_name(nvdimm)); return -ENOMEM; } @@ -2391,15 +2388,15 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, rc = nfit_blk_init_interleave(mmio, nfit_mem->idt_dcr, nfit_mem->memdev_dcr->interleave_ways); if (rc) { - dev_dbg(dev, "%s: %s failed to init dcr interleave\n", - __func__, nvdimm_name(nvdimm)); + dev_dbg(dev, "%s failed to init dcr interleave\n", + nvdimm_name(nvdimm)); return rc; } rc = acpi_nfit_blk_get_flags(nd_desc, nvdimm, nfit_blk); if (rc < 0) { - dev_dbg(dev, "%s: %s failed get DIMM flags\n", - __func__, nvdimm_name(nvdimm)); + dev_dbg(dev, "%s failed get DIMM flags\n", + nvdimm_name(nvdimm)); return rc; } @@ -2449,7 +2446,8 @@ static int ars_start(struct acpi_nfit_desc *acpi_desc, struct nfit_spa *nfit_spa memset(&ars_start, 0, sizeof(ars_start)); ars_start.address = spa->address; ars_start.length = spa->length; - ars_start.flags = acpi_desc->ars_start_flags; + if (test_bit(ARS_SHORT, &nfit_spa->ars_state)) + ars_start.flags = ND_ARS_RETURN_PREV_DATA; if (nfit_spa_type(spa) == NFIT_SPA_PM) ars_start.type = ND_ARS_PERSISTENT; else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) @@ -2491,16 +2489,62 @@ static int ars_get_status(struct acpi_nfit_desc *acpi_desc) int rc, cmd_rc; rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, ars_status, - acpi_desc->ars_status_size, &cmd_rc); + acpi_desc->max_ars, &cmd_rc); if (rc < 0) return rc; return cmd_rc; } -static int ars_status_process_records(struct acpi_nfit_desc *acpi_desc, - struct nd_cmd_ars_status *ars_status) +static void ars_complete(struct acpi_nfit_desc *acpi_desc, + struct nfit_spa *nfit_spa) +{ + struct nd_cmd_ars_status *ars_status = acpi_desc->ars_status; + struct acpi_nfit_system_address *spa = nfit_spa->spa; + struct nd_region *nd_region = nfit_spa->nd_region; + struct device *dev; + + if ((ars_status->address >= spa->address && ars_status->address + < spa->address + spa->length) + || (ars_status->address < spa->address)) { + /* + * Assume that if a scrub starts at an offset from the + * start of nfit_spa that we are in the continuation + * case. + * + * Otherwise, if the scrub covers the spa range, mark + * any pending request complete. + */ + if (ars_status->address + ars_status->length + >= spa->address + spa->length) + /* complete */; + else + return; + } else + return; + + if (test_bit(ARS_DONE, &nfit_spa->ars_state)) + return; + + if (!test_and_clear_bit(ARS_REQ, &nfit_spa->ars_state)) + return; + + if (nd_region) { + dev = nd_region_dev(nd_region); + nvdimm_region_notify(nd_region, NVDIMM_REVALIDATE_POISON); + } else + dev = acpi_desc->dev; + + dev_dbg(dev, "ARS: range %d %s complete\n", spa->range_index, + test_bit(ARS_SHORT, &nfit_spa->ars_state) + ? "short" : "long"); + clear_bit(ARS_SHORT, &nfit_spa->ars_state); + set_bit(ARS_DONE, &nfit_spa->ars_state); +} + +static int ars_status_process_records(struct acpi_nfit_desc *acpi_desc) { struct nvdimm_bus *nvdimm_bus = acpi_desc->nvdimm_bus; + struct nd_cmd_ars_status *ars_status = acpi_desc->ars_status; int rc; u32 i; @@ -2579,7 +2623,7 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, struct acpi_nfit_system_address *spa = nfit_spa->spa; struct nd_blk_region_desc *ndbr_desc; struct nfit_mem *nfit_mem; - int blk_valid = 0, rc; + int rc; if (!nvdimm) { dev_err(acpi_desc->dev, "spa%d dimm: %#x not found\n", @@ -2599,15 +2643,14 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, if (!nfit_mem || !nfit_mem->bdw) { dev_dbg(acpi_desc->dev, "spa%d %s missing bdw\n", spa->range_index, nvdimm_name(nvdimm)); - } else { - mapping->size = nfit_mem->bdw->capacity; - mapping->start = nfit_mem->bdw->start_address; - ndr_desc->num_lanes = nfit_mem->bdw->windows; - blk_valid = 1; + break; } + mapping->size = nfit_mem->bdw->capacity; + mapping->start = nfit_mem->bdw->start_address; + ndr_desc->num_lanes = nfit_mem->bdw->windows; ndr_desc->mapping = mapping; - ndr_desc->num_mappings = blk_valid; + ndr_desc->num_mappings = 1; ndbr_desc = to_blk_region_desc(ndr_desc); ndbr_desc->enable = acpi_nfit_blk_region_enable; ndbr_desc->do_io = acpi_desc->blk_do_io; @@ -2655,8 +2698,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, return 0; if (spa->range_index == 0 && !nfit_spa_is_virtual(spa)) { - dev_dbg(acpi_desc->dev, "%s: detected invalid spa index\n", - __func__); + dev_dbg(acpi_desc->dev, "detected invalid spa index\n"); return 0; } @@ -2742,301 +2784,243 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, return rc; } -static int ars_status_alloc(struct acpi_nfit_desc *acpi_desc, - u32 max_ars) +static int ars_status_alloc(struct acpi_nfit_desc *acpi_desc) { struct device *dev = acpi_desc->dev; struct nd_cmd_ars_status *ars_status; - if (acpi_desc->ars_status && acpi_desc->ars_status_size >= max_ars) { - memset(acpi_desc->ars_status, 0, acpi_desc->ars_status_size); + if (acpi_desc->ars_status) { + memset(acpi_desc->ars_status, 0, acpi_desc->max_ars); return 0; } - if (acpi_desc->ars_status) - devm_kfree(dev, acpi_desc->ars_status); - acpi_desc->ars_status = NULL; - ars_status = devm_kzalloc(dev, max_ars, GFP_KERNEL); + ars_status = devm_kzalloc(dev, acpi_desc->max_ars, GFP_KERNEL); if (!ars_status) return -ENOMEM; acpi_desc->ars_status = ars_status; - acpi_desc->ars_status_size = max_ars; return 0; } -static int acpi_nfit_query_poison(struct acpi_nfit_desc *acpi_desc, - struct nfit_spa *nfit_spa) +static int acpi_nfit_query_poison(struct acpi_nfit_desc *acpi_desc) { - struct acpi_nfit_system_address *spa = nfit_spa->spa; int rc; - if (!nfit_spa->max_ars) { - struct nd_cmd_ars_cap ars_cap; - - memset(&ars_cap, 0, sizeof(ars_cap)); - rc = ars_get_cap(acpi_desc, &ars_cap, nfit_spa); - if (rc < 0) - return rc; - nfit_spa->max_ars = ars_cap.max_ars_out; - nfit_spa->clear_err_unit = ars_cap.clear_err_unit; - /* check that the supported scrub types match the spa type */ - if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE && - ((ars_cap.status >> 16) & ND_ARS_VOLATILE) == 0) - return -ENOTTY; - else if (nfit_spa_type(spa) == NFIT_SPA_PM && - ((ars_cap.status >> 16) & ND_ARS_PERSISTENT) == 0) - return -ENOTTY; - } - - if (ars_status_alloc(acpi_desc, nfit_spa->max_ars)) + if (ars_status_alloc(acpi_desc)) return -ENOMEM; rc = ars_get_status(acpi_desc); + if (rc < 0 && rc != -ENOSPC) return rc; - if (ars_status_process_records(acpi_desc, acpi_desc->ars_status)) + if (ars_status_process_records(acpi_desc)) return -ENOMEM; return 0; } -static void acpi_nfit_async_scrub(struct acpi_nfit_desc *acpi_desc, - struct nfit_spa *nfit_spa) +static int ars_register(struct acpi_nfit_desc *acpi_desc, struct nfit_spa *nfit_spa, + int *query_rc) { - struct acpi_nfit_system_address *spa = nfit_spa->spa; - unsigned int overflow_retry = scrub_overflow_abort; - u64 init_ars_start = 0, init_ars_len = 0; - struct device *dev = acpi_desc->dev; - unsigned int tmo = scrub_timeout; - int rc; + int rc = *query_rc; - if (!nfit_spa->ars_required || !nfit_spa->nd_region) - return; + if (no_init_ars) + return acpi_nfit_register_region(acpi_desc, nfit_spa); - rc = ars_start(acpi_desc, nfit_spa); - /* - * If we timed out the initial scan we'll still be busy here, - * and will wait another timeout before giving up permanently. - */ - if (rc < 0 && rc != -EBUSY) - return; - - do { - u64 ars_start, ars_len; - - if (acpi_desc->cancel) - break; - rc = acpi_nfit_query_poison(acpi_desc, nfit_spa); - if (rc == -ENOTTY) - break; - if (rc == -EBUSY && !tmo) { - dev_warn(dev, "range %d ars timeout, aborting\n", - spa->range_index); - break; - } + set_bit(ARS_REQ, &nfit_spa->ars_state); + set_bit(ARS_SHORT, &nfit_spa->ars_state); + switch (rc) { + case 0: + case -EAGAIN: + rc = ars_start(acpi_desc, nfit_spa); if (rc == -EBUSY) { - /* - * Note, entries may be appended to the list - * while the lock is dropped, but the workqueue - * being active prevents entries being deleted / - * freed. - */ - mutex_unlock(&acpi_desc->init_mutex); - ssleep(1); - tmo--; - mutex_lock(&acpi_desc->init_mutex); - continue; - } - - /* we got some results, but there are more pending... */ - if (rc == -ENOSPC && overflow_retry--) { - if (!init_ars_len) { - init_ars_len = acpi_desc->ars_status->length; - init_ars_start = acpi_desc->ars_status->address; - } - rc = ars_continue(acpi_desc); - } - - if (rc < 0) { - dev_warn(dev, "range %d ars continuation failed\n", - spa->range_index); + *query_rc = rc; break; - } - - if (init_ars_len) { - ars_start = init_ars_start; - ars_len = init_ars_len; + } else if (rc == 0) { + rc = acpi_nfit_query_poison(acpi_desc); } else { - ars_start = acpi_desc->ars_status->address; - ars_len = acpi_desc->ars_status->length; + set_bit(ARS_FAILED, &nfit_spa->ars_state); + break; } - dev_dbg(dev, "spa range: %d ars from %#llx + %#llx complete\n", - spa->range_index, ars_start, ars_len); - /* notify the region about new poison entries */ - nvdimm_region_notify(nfit_spa->nd_region, - NVDIMM_REVALIDATE_POISON); + if (rc == -EAGAIN) + clear_bit(ARS_SHORT, &nfit_spa->ars_state); + else if (rc == 0) + ars_complete(acpi_desc, nfit_spa); break; - } while (1); + case -EBUSY: + case -ENOSPC: + break; + default: + set_bit(ARS_FAILED, &nfit_spa->ars_state); + break; + } + + if (test_and_clear_bit(ARS_DONE, &nfit_spa->ars_state)) + set_bit(ARS_REQ, &nfit_spa->ars_state); + + return acpi_nfit_register_region(acpi_desc, nfit_spa); } -static void acpi_nfit_scrub(struct work_struct *work) +static void ars_complete_all(struct acpi_nfit_desc *acpi_desc) { - struct device *dev; - u64 init_scrub_length = 0; struct nfit_spa *nfit_spa; - u64 init_scrub_address = 0; - bool init_ars_done = false; - struct acpi_nfit_desc *acpi_desc; - unsigned int tmo = scrub_timeout; - unsigned int overflow_retry = scrub_overflow_abort; - - acpi_desc = container_of(work, typeof(*acpi_desc), work); - dev = acpi_desc->dev; - - /* - * We scrub in 2 phases. The first phase waits for any platform - * firmware initiated scrubs to complete and then we go search for the - * affected spa regions to mark them scanned. In the second phase we - * initiate a directed scrub for every range that was not scrubbed in - * phase 1. If we're called for a 'rescan', we harmlessly pass through - * the first phase, but really only care about running phase 2, where - * regions can be notified of new poison. - */ - /* process platform firmware initiated scrubs */ - retry: - mutex_lock(&acpi_desc->init_mutex); list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { - struct nd_cmd_ars_status *ars_status; - struct acpi_nfit_system_address *spa; - u64 ars_start, ars_len; - int rc; - - if (acpi_desc->cancel) - break; - - if (nfit_spa->nd_region) + if (test_bit(ARS_FAILED, &nfit_spa->ars_state)) continue; + ars_complete(acpi_desc, nfit_spa); + } +} - if (init_ars_done) { - /* - * No need to re-query, we're now just - * reconciling all the ranges covered by the - * initial scrub - */ - rc = 0; - } else - rc = acpi_nfit_query_poison(acpi_desc, nfit_spa); - - if (rc == -ENOTTY) { - /* no ars capability, just register spa and move on */ - acpi_nfit_register_region(acpi_desc, nfit_spa); - continue; - } - - if (rc == -EBUSY && !tmo) { - /* fallthrough to directed scrub in phase 2 */ - dev_warn(dev, "timeout awaiting ars results, continuing...\n"); - break; - } else if (rc == -EBUSY) { - mutex_unlock(&acpi_desc->init_mutex); - ssleep(1); - tmo--; - goto retry; - } - - /* we got some results, but there are more pending... */ - if (rc == -ENOSPC && overflow_retry--) { - ars_status = acpi_desc->ars_status; - /* - * Record the original scrub range, so that we - * can recall all the ranges impacted by the - * initial scrub. - */ - if (!init_scrub_length) { - init_scrub_length = ars_status->length; - init_scrub_address = ars_status->address; - } - rc = ars_continue(acpi_desc); - if (rc == 0) { - mutex_unlock(&acpi_desc->init_mutex); - goto retry; - } - } +static unsigned int __acpi_nfit_scrub(struct acpi_nfit_desc *acpi_desc, + int query_rc) +{ + unsigned int tmo = acpi_desc->scrub_tmo; + struct device *dev = acpi_desc->dev; + struct nfit_spa *nfit_spa; - if (rc < 0) { - /* - * Initial scrub failed, we'll give it one more - * try below... - */ - break; - } + if (acpi_desc->cancel) + return 0; - /* We got some final results, record completed ranges */ - ars_status = acpi_desc->ars_status; - if (init_scrub_length) { - ars_start = init_scrub_address; - ars_len = ars_start + init_scrub_length; - } else { - ars_start = ars_status->address; - ars_len = ars_status->length; - } - spa = nfit_spa->spa; + if (query_rc == -EBUSY) { + dev_dbg(dev, "ARS: ARS busy\n"); + return min(30U * 60U, tmo * 2); + } + if (query_rc == -ENOSPC) { + dev_dbg(dev, "ARS: ARS continue\n"); + ars_continue(acpi_desc); + return 1; + } + if (query_rc && query_rc != -EAGAIN) { + unsigned long long addr, end; - if (!init_ars_done) { - init_ars_done = true; - dev_dbg(dev, "init scrub %#llx + %#llx complete\n", - ars_start, ars_len); - } - if (ars_start <= spa->address && ars_start + ars_len - >= spa->address + spa->length) - acpi_nfit_register_region(acpi_desc, nfit_spa); + addr = acpi_desc->ars_status->address; + end = addr + acpi_desc->ars_status->length; + dev_dbg(dev, "ARS: %llx-%llx failed (%d)\n", addr, end, + query_rc); } - /* - * For all the ranges not covered by an initial scrub we still - * want to see if there are errors, but it's ok to discover them - * asynchronously. - */ + ars_complete_all(acpi_desc); list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { - /* - * Flag all the ranges that still need scrubbing, but - * register them now to make data available. - */ - if (!nfit_spa->nd_region) { - nfit_spa->ars_required = 1; - acpi_nfit_register_region(acpi_desc, nfit_spa); + if (test_bit(ARS_FAILED, &nfit_spa->ars_state)) + continue; + if (test_bit(ARS_REQ, &nfit_spa->ars_state)) { + int rc = ars_start(acpi_desc, nfit_spa); + + clear_bit(ARS_DONE, &nfit_spa->ars_state); + dev = nd_region_dev(nfit_spa->nd_region); + dev_dbg(dev, "ARS: range %d ARS start (%d)\n", + nfit_spa->spa->range_index, rc); + if (rc == 0 || rc == -EBUSY) + return 1; + dev_err(dev, "ARS: range %d ARS failed (%d)\n", + nfit_spa->spa->range_index, rc); + set_bit(ARS_FAILED, &nfit_spa->ars_state); } } - acpi_desc->init_complete = 1; + return 0; +} - list_for_each_entry(nfit_spa, &acpi_desc->spas, list) - acpi_nfit_async_scrub(acpi_desc, nfit_spa); - acpi_desc->scrub_count++; - acpi_desc->ars_start_flags = 0; - if (acpi_desc->scrub_count_state) - sysfs_notify_dirent(acpi_desc->scrub_count_state); +static void acpi_nfit_scrub(struct work_struct *work) +{ + struct acpi_nfit_desc *acpi_desc; + unsigned int tmo; + int query_rc; + + acpi_desc = container_of(work, typeof(*acpi_desc), dwork.work); + mutex_lock(&acpi_desc->init_mutex); + query_rc = acpi_nfit_query_poison(acpi_desc); + tmo = __acpi_nfit_scrub(acpi_desc, query_rc); + if (tmo) { + queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ); + acpi_desc->scrub_tmo = tmo; + } else { + acpi_desc->scrub_count++; + if (acpi_desc->scrub_count_state) + sysfs_notify_dirent(acpi_desc->scrub_count_state); + } + memset(acpi_desc->ars_status, 0, acpi_desc->max_ars); mutex_unlock(&acpi_desc->init_mutex); } +static void acpi_nfit_init_ars(struct acpi_nfit_desc *acpi_desc, + struct nfit_spa *nfit_spa) +{ + int type = nfit_spa_type(nfit_spa->spa); + struct nd_cmd_ars_cap ars_cap; + int rc; + + memset(&ars_cap, 0, sizeof(ars_cap)); + rc = ars_get_cap(acpi_desc, &ars_cap, nfit_spa); + if (rc < 0) + return; + /* check that the supported scrub types match the spa type */ + if (type == NFIT_SPA_VOLATILE && ((ars_cap.status >> 16) + & ND_ARS_VOLATILE) == 0) + return; + if (type == NFIT_SPA_PM && ((ars_cap.status >> 16) + & ND_ARS_PERSISTENT) == 0) + return; + + nfit_spa->max_ars = ars_cap.max_ars_out; + nfit_spa->clear_err_unit = ars_cap.clear_err_unit; + acpi_desc->max_ars = max(nfit_spa->max_ars, acpi_desc->max_ars); + clear_bit(ARS_FAILED, &nfit_spa->ars_state); + set_bit(ARS_REQ, &nfit_spa->ars_state); +} + static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc) { struct nfit_spa *nfit_spa; - int rc; + int rc, query_rc; + + list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { + set_bit(ARS_FAILED, &nfit_spa->ars_state); + switch (nfit_spa_type(nfit_spa->spa)) { + case NFIT_SPA_VOLATILE: + case NFIT_SPA_PM: + acpi_nfit_init_ars(acpi_desc, nfit_spa); + break; + } + } + + /* + * Reap any results that might be pending before starting new + * short requests. + */ + query_rc = acpi_nfit_query_poison(acpi_desc); + if (query_rc == 0) + ars_complete_all(acpi_desc); list_for_each_entry(nfit_spa, &acpi_desc->spas, list) - if (nfit_spa_type(nfit_spa->spa) == NFIT_SPA_DCR) { - /* BLK regions don't need to wait for ars results */ + switch (nfit_spa_type(nfit_spa->spa)) { + case NFIT_SPA_VOLATILE: + case NFIT_SPA_PM: + /* register regions and kick off initial ARS run */ + rc = ars_register(acpi_desc, nfit_spa, &query_rc); + if (rc) + return rc; + break; + case NFIT_SPA_BDW: + /* nothing to register */ + break; + case NFIT_SPA_DCR: + case NFIT_SPA_VDISK: + case NFIT_SPA_VCD: + case NFIT_SPA_PDISK: + case NFIT_SPA_PCD: + /* register known regions that don't support ARS */ rc = acpi_nfit_register_region(acpi_desc, nfit_spa); if (rc) return rc; + break; + default: + /* don't register unknown regions */ + break; } - acpi_desc->ars_start_flags = 0; - if (!acpi_desc->cancel) - queue_work(nfit_wq, &acpi_desc->work); + queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0); return 0; } @@ -3146,8 +3130,7 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *data, acpi_size sz) data = add_table(acpi_desc, &prev, data, end); if (IS_ERR(data)) { - dev_dbg(dev, "%s: nfit table parsing error: %ld\n", __func__, - PTR_ERR(data)); + dev_dbg(dev, "nfit table parsing error: %ld\n", PTR_ERR(data)); rc = PTR_ERR(data); goto out_unlock; } @@ -3172,49 +3155,20 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *data, acpi_size sz) } EXPORT_SYMBOL_GPL(acpi_nfit_init); -struct acpi_nfit_flush_work { - struct work_struct work; - struct completion cmp; -}; - -static void flush_probe(struct work_struct *work) -{ - struct acpi_nfit_flush_work *flush; - - flush = container_of(work, typeof(*flush), work); - complete(&flush->cmp); -} - static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc) { struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc); struct device *dev = acpi_desc->dev; - struct acpi_nfit_flush_work flush; - int rc; - /* bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */ + /* Bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */ device_lock(dev); device_unlock(dev); - /* bounce the init_mutex to make init_complete valid */ + /* Bounce the init_mutex to complete initial registration */ mutex_lock(&acpi_desc->init_mutex); - if (acpi_desc->cancel || acpi_desc->init_complete) { - mutex_unlock(&acpi_desc->init_mutex); - return 0; - } - - /* - * Scrub work could take 10s of seconds, userspace may give up so we - * need to be interruptible while waiting. - */ - INIT_WORK_ONSTACK(&flush.work, flush_probe); - init_completion(&flush.cmp); - queue_work(nfit_wq, &flush.work); mutex_unlock(&acpi_desc->init_mutex); - rc = wait_for_completion_interruptible(&flush.cmp); - cancel_work_sync(&flush.work); - return rc; + return 0; } static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, @@ -3233,20 +3187,18 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, * just needs guarantees that any ars it initiates are not * interrupted by any intervening start reqeusts from userspace. */ - if (work_busy(&acpi_desc->work)) + if (work_busy(&acpi_desc->dwork.work)) return -EBUSY; return 0; } -int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, u8 flags) +int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, unsigned long flags) { struct device *dev = acpi_desc->dev; + int scheduled = 0, busy = 0; struct nfit_spa *nfit_spa; - if (work_busy(&acpi_desc->work)) - return -EBUSY; - mutex_lock(&acpi_desc->init_mutex); if (acpi_desc->cancel) { mutex_unlock(&acpi_desc->init_mutex); @@ -3254,19 +3206,32 @@ int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, u8 flags) } list_for_each_entry(nfit_spa, &acpi_desc->spas, list) { - struct acpi_nfit_system_address *spa = nfit_spa->spa; + int type = nfit_spa_type(nfit_spa->spa); - if (nfit_spa_type(spa) != NFIT_SPA_PM) + if (type != NFIT_SPA_PM && type != NFIT_SPA_VOLATILE) + continue; + if (test_bit(ARS_FAILED, &nfit_spa->ars_state)) continue; - nfit_spa->ars_required = 1; + if (test_and_set_bit(ARS_REQ, &nfit_spa->ars_state)) + busy++; + else { + if (test_bit(ARS_SHORT, &flags)) + set_bit(ARS_SHORT, &nfit_spa->ars_state); + scheduled++; + } + } + if (scheduled) { + queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0); + dev_dbg(dev, "ars_scan triggered\n"); } - acpi_desc->ars_start_flags = flags; - queue_work(nfit_wq, &acpi_desc->work); - dev_dbg(dev, "%s: ars_scan triggered\n", __func__); mutex_unlock(&acpi_desc->init_mutex); - return 0; + if (scheduled) + return 0; + if (busy) + return -EBUSY; + return -ENOTTY; } void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev) @@ -3293,7 +3258,8 @@ void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev) INIT_LIST_HEAD(&acpi_desc->dimms); INIT_LIST_HEAD(&acpi_desc->list); mutex_init(&acpi_desc->init_mutex); - INIT_WORK(&acpi_desc->work, acpi_nfit_scrub); + acpi_desc->scrub_tmo = 1; + INIT_DELAYED_WORK(&acpi_desc->dwork, acpi_nfit_scrub); } EXPORT_SYMBOL_GPL(acpi_nfit_desc_init); @@ -3317,6 +3283,7 @@ void acpi_nfit_shutdown(void *data) mutex_lock(&acpi_desc->init_mutex); acpi_desc->cancel = 1; + cancel_delayed_work_sync(&acpi_desc->dwork); mutex_unlock(&acpi_desc->init_mutex); /* @@ -3370,8 +3337,8 @@ static int acpi_nfit_add(struct acpi_device *adev) rc = acpi_nfit_init(acpi_desc, obj->buffer.pointer, obj->buffer.length); else - dev_dbg(dev, "%s invalid type %d, ignoring _FIT\n", - __func__, (int) obj->type); + dev_dbg(dev, "invalid type %d, ignoring _FIT\n", + (int) obj->type); kfree(buf.pointer); } else /* skip over the lead-in header table */ @@ -3400,7 +3367,7 @@ static void acpi_nfit_update_notify(struct device *dev, acpi_handle handle) if (!dev->driver) { /* dev->driver may be null if we're being removed */ - dev_dbg(dev, "%s: no driver found for dev\n", __func__); + dev_dbg(dev, "no driver found for dev\n"); return; } @@ -3438,15 +3405,15 @@ static void acpi_nfit_update_notify(struct device *dev, acpi_handle handle) static void acpi_nfit_uc_error_notify(struct device *dev, acpi_handle handle) { struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(dev); - u8 flags = (acpi_desc->scrub_mode == HW_ERROR_SCRUB_ON) ? - 0 : ND_ARS_RETURN_PREV_DATA; + unsigned long flags = (acpi_desc->scrub_mode == HW_ERROR_SCRUB_ON) ? + 0 : 1 << ARS_SHORT; acpi_nfit_ars_rescan(acpi_desc, flags); } void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event) { - dev_dbg(dev, "%s: event: 0x%x\n", __func__, event); + dev_dbg(dev, "event: 0x%x\n", event); switch (event) { case NFIT_NOTIFY_UPDATE: diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c index b92921439657..e9626bf6ca29 100644 --- a/drivers/acpi/nfit/mce.c +++ b/drivers/acpi/nfit/mce.c @@ -51,9 +51,8 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val, if ((spa->address + spa->length - 1) < mce->addr) continue; found_match = 1; - dev_dbg(dev, "%s: addr in SPA %d (0x%llx, 0x%llx)\n", - __func__, spa->range_index, spa->address, - spa->length); + dev_dbg(dev, "addr in SPA %d (0x%llx, 0x%llx)\n", + spa->range_index, spa->address, spa->length); /* * We can break at the first match because we're going * to rescan all the SPA ranges. There shouldn't be any diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index 50d36e166d70..7d15856a739f 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -117,10 +117,17 @@ enum nfit_dimm_notifiers { NFIT_NOTIFY_DIMM_HEALTH = 0x81, }; +enum nfit_ars_state { + ARS_REQ, + ARS_DONE, + ARS_SHORT, + ARS_FAILED, +}; + struct nfit_spa { struct list_head list; struct nd_region *nd_region; - unsigned int ars_required:1; + unsigned long ars_state; u32 clear_err_unit; u32 max_ars; struct acpi_nfit_system_address spa[0]; @@ -171,9 +178,8 @@ struct nfit_mem { struct resource *flush_wpq; unsigned long dsm_mask; int family; - u32 has_lsi:1; - u32 has_lsr:1; - u32 has_lsw:1; + bool has_lsr; + bool has_lsw; }; struct acpi_nfit_desc { @@ -191,18 +197,18 @@ struct acpi_nfit_desc { struct device *dev; u8 ars_start_flags; struct nd_cmd_ars_status *ars_status; - size_t ars_status_size; - struct work_struct work; + struct delayed_work dwork; struct list_head list; struct kernfs_node *scrub_count_state; + unsigned int max_ars; unsigned int scrub_count; unsigned int scrub_mode; unsigned int cancel:1; - unsigned int init_complete:1; unsigned long dimm_cmd_force_en; unsigned long bus_cmd_force_en; unsigned long bus_nfit_cmd_force_en; unsigned int platform_cap; + unsigned int scrub_tmo; int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, void *iobuf, u64 len, int rw); }; @@ -244,7 +250,7 @@ struct nfit_blk { extern struct list_head acpi_descs; extern struct mutex acpi_desc_lock; -int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, u8 flags); +int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, unsigned long flags); #ifdef CONFIG_X86_MCE void nfit_mce_register(void); diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 2137dbc29877..37be5a306c8f 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -257,8 +257,8 @@ static int __dev_dax_pte_fault(struct dev_dax *dev_dax, struct vm_fault *vmf) dax_region = dev_dax->region; if (dax_region->align > PAGE_SIZE) { - dev_dbg(dev, "%s: alignment (%#x) > fault size (%#x)\n", - __func__, dax_region->align, fault_size); + dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n", + dax_region->align, fault_size); return VM_FAULT_SIGBUS; } @@ -267,8 +267,7 @@ static int __dev_dax_pte_fault(struct dev_dax *dev_dax, struct vm_fault *vmf) phys = dax_pgoff_to_phys(dev_dax, vmf->pgoff, PAGE_SIZE); if (phys == -1) { - dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__, - vmf->pgoff); + dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", vmf->pgoff); return VM_FAULT_SIGBUS; } @@ -299,14 +298,14 @@ static int __dev_dax_pmd_fault(struct dev_dax *dev_dax, struct vm_fault *vmf) dax_region = dev_dax->region; if (dax_region->align > PMD_SIZE) { - dev_dbg(dev, "%s: alignment (%#x) > fault size (%#x)\n", - __func__, dax_region->align, fault_size); + dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n", + dax_region->align, fault_size); return VM_FAULT_SIGBUS; } /* dax pmd mappings require pfn_t_devmap() */ if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) { - dev_dbg(dev, "%s: region lacks devmap flags\n", __func__); + dev_dbg(dev, "region lacks devmap flags\n"); return VM_FAULT_SIGBUS; } @@ -323,8 +322,7 @@ static int __dev_dax_pmd_fault(struct dev_dax *dev_dax, struct vm_fault *vmf) pgoff = linear_page_index(vmf->vma, pmd_addr); phys = dax_pgoff_to_phys(dev_dax, pgoff, PMD_SIZE); if (phys == -1) { - dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__, - pgoff); + dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", pgoff); return VM_FAULT_SIGBUS; } @@ -351,14 +349,14 @@ static int __dev_dax_pud_fault(struct dev_dax *dev_dax, struct vm_fault *vmf) dax_region = dev_dax->region; if (dax_region->align > PUD_SIZE) { - dev_dbg(dev, "%s: alignment (%#x) > fault size (%#x)\n", - __func__, dax_region->align, fault_size); + dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n", + dax_region->align, fault_size); return VM_FAULT_SIGBUS; } /* dax pud mappings require pfn_t_devmap() */ if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) { - dev_dbg(dev, "%s: region lacks devmap flags\n", __func__); + dev_dbg(dev, "region lacks devmap flags\n"); return VM_FAULT_SIGBUS; } @@ -375,8 +373,7 @@ static int __dev_dax_pud_fault(struct dev_dax *dev_dax, struct vm_fault *vmf) pgoff = linear_page_index(vmf->vma, pud_addr); phys = dax_pgoff_to_phys(dev_dax, pgoff, PUD_SIZE); if (phys == -1) { - dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__, - pgoff); + dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", pgoff); return VM_FAULT_SIGBUS; } @@ -399,9 +396,8 @@ static int dev_dax_huge_fault(struct vm_fault *vmf, struct file *filp = vmf->vma->vm_file; struct dev_dax *dev_dax = filp->private_data; - dev_dbg(&dev_dax->dev, "%s: %s: %s (%#lx - %#lx) size = %d\n", __func__, - current->comm, (vmf->flags & FAULT_FLAG_WRITE) - ? "write" : "read", + dev_dbg(&dev_dax->dev, "%s: %s (%#lx - %#lx) size = %d\n", current->comm, + (vmf->flags & FAULT_FLAG_WRITE) ? "write" : "read", vmf->vma->vm_start, vmf->vma->vm_end, pe_size); id = dax_read_lock(); @@ -450,7 +446,7 @@ static int dax_mmap(struct file *filp, struct vm_area_struct *vma) struct dev_dax *dev_dax = filp->private_data; int rc, id; - dev_dbg(&dev_dax->dev, "%s\n", __func__); + dev_dbg(&dev_dax->dev, "trace\n"); /* * We lock to check dax_dev liveness and will re-check at @@ -508,7 +504,7 @@ static int dax_open(struct inode *inode, struct file *filp) struct inode *__dax_inode = dax_inode(dax_dev); struct dev_dax *dev_dax = dax_get_private(dax_dev); - dev_dbg(&dev_dax->dev, "%s\n", __func__); + dev_dbg(&dev_dax->dev, "trace\n"); inode->i_mapping = __dax_inode->i_mapping; inode->i_mapping->host = __dax_inode; filp->f_mapping = inode->i_mapping; @@ -523,7 +519,7 @@ static int dax_release(struct inode *inode, struct file *filp) { struct dev_dax *dev_dax = filp->private_data; - dev_dbg(&dev_dax->dev, "%s\n", __func__); + dev_dbg(&dev_dax->dev, "trace\n"); return 0; } @@ -565,7 +561,7 @@ static void unregister_dev_dax(void *dev) struct inode *inode = dax_inode(dax_dev); struct cdev *cdev = inode->i_cdev; - dev_dbg(dev, "%s\n", __func__); + dev_dbg(dev, "trace\n"); kill_dev_dax(dev_dax); cdev_device_del(cdev, dev); diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index 31b6ecce4c64..fd49b24fd6af 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -34,7 +34,7 @@ static void dax_pmem_percpu_release(struct percpu_ref *ref) { struct dax_pmem *dax_pmem = to_dax_pmem(ref); - dev_dbg(dax_pmem->dev, "%s\n", __func__); + dev_dbg(dax_pmem->dev, "trace\n"); complete(&dax_pmem->cmp); } @@ -43,7 +43,7 @@ static void dax_pmem_percpu_exit(void *data) struct percpu_ref *ref = data; struct dax_pmem *dax_pmem = to_dax_pmem(ref); - dev_dbg(dax_pmem->dev, "%s\n", __func__); + dev_dbg(dax_pmem->dev, "trace\n"); wait_for_completion(&dax_pmem->cmp); percpu_ref_exit(ref); } @@ -53,7 +53,7 @@ static void dax_pmem_percpu_kill(void *data) struct percpu_ref *ref = data; struct dax_pmem *dax_pmem = to_dax_pmem(ref); - dev_dbg(dax_pmem->dev, "%s\n", __func__); + dev_dbg(dax_pmem->dev, "trace\n"); percpu_ref_kill(ref); } @@ -150,17 +150,7 @@ static struct nd_device_driver dax_pmem_driver = { .type = ND_DRIVER_DAX_PMEM, }; -static int __init dax_pmem_init(void) -{ - return nd_driver_register(&dax_pmem_driver); -} -module_init(dax_pmem_init); - -static void __exit dax_pmem_exit(void) -{ - driver_unregister(&dax_pmem_driver.drv); -} -module_exit(dax_pmem_exit); +module_nd_driver(dax_pmem_driver); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Intel Corporation"); diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index a65f2e1d9f53..f6c533c4d09b 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -102,4 +102,15 @@ config NVDIMM_DAX Select Y if unsure +config OF_PMEM + # FIXME: make tristate once OF_NUMA dependency removed + bool "Device-tree support for persistent memory regions" + depends on OF + default LIBNVDIMM + help + Allows regions of persistent memory to be described in the + device-tree. + + Select Y if unsure. + endif diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile index 70d5f3ad9909..e8847045dac0 100644 --- a/drivers/nvdimm/Makefile +++ b/drivers/nvdimm/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o obj-$(CONFIG_ND_BTT) += nd_btt.o obj-$(CONFIG_ND_BLK) += nd_blk.o obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o +obj-$(CONFIG_OF_PMEM) += of_pmem.o nd_pmem-y := pmem.o diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index d58925295aa7..795ad4ff35ca 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -26,7 +26,7 @@ static void nd_btt_release(struct device *dev) struct nd_region *nd_region = to_nd_region(dev->parent); struct nd_btt *nd_btt = to_nd_btt(dev); - dev_dbg(dev, "%s\n", __func__); + dev_dbg(dev, "trace\n"); nd_detach_ndns(&nd_btt->dev, &nd_btt->ndns); ida_simple_remove(&nd_region->btt_ida, nd_btt->id); kfree(nd_btt->uuid); @@ -74,8 +74,8 @@ static ssize_t sector_size_store(struct device *dev, nvdimm_bus_lock(dev); rc = nd_size_select_store(dev, buf, &nd_btt->lbasize, btt_lbasize_supported); - dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__, - rc, buf, buf[len - 1] == '\n' ? "" : "\n"); + dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, + buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); device_unlock(dev); @@ -101,8 +101,8 @@ static ssize_t uuid_store(struct device *dev, device_lock(dev); rc = nd_uuid_store(dev, &nd_btt->uuid, buf, len); - dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__, - rc, buf, buf[len - 1] == '\n' ? "" : "\n"); + dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, + buf[len - 1] == '\n' ? "" : "\n"); device_unlock(dev); return rc ? rc : len; @@ -131,8 +131,8 @@ static ssize_t namespace_store(struct device *dev, device_lock(dev); nvdimm_bus_lock(dev); rc = nd_namespace_store(dev, &nd_btt->ndns, buf, len); - dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__, - rc, buf, buf[len - 1] == '\n' ? "" : "\n"); + dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, + buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); device_unlock(dev); @@ -206,8 +206,8 @@ static struct device *__nd_btt_create(struct nd_region *nd_region, dev->groups = nd_btt_attribute_groups; device_initialize(&nd_btt->dev); if (ndns && !__nd_attach_ndns(&nd_btt->dev, ndns, &nd_btt->ndns)) { - dev_dbg(&ndns->dev, "%s failed, already claimed by %s\n", - __func__, dev_name(ndns->claim)); + dev_dbg(&ndns->dev, "failed, already claimed by %s\n", + dev_name(ndns->claim)); put_device(dev); return NULL; } @@ -346,8 +346,7 @@ int nd_btt_probe(struct device *dev, struct nd_namespace_common *ndns) return -ENOMEM; btt_sb = devm_kzalloc(dev, sizeof(*btt_sb), GFP_KERNEL); rc = __nd_btt_probe(to_nd_btt(btt_dev), ndns, btt_sb); - dev_dbg(dev, "%s: btt: %s\n", __func__, - rc == 0 ? dev_name(btt_dev) : "<none>"); + dev_dbg(dev, "btt: %s\n", rc == 0 ? dev_name(btt_dev) : "<none>"); if (rc < 0) { struct nd_btt *nd_btt = to_nd_btt(btt_dev); diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 78eabc3a1ab1..a64023690cad 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -358,6 +358,7 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent, nvdimm_bus->dev.release = nvdimm_bus_release; nvdimm_bus->dev.groups = nd_desc->attr_groups; nvdimm_bus->dev.bus = &nvdimm_bus_type; + nvdimm_bus->dev.of_node = nd_desc->of_node; dev_set_name(&nvdimm_bus->dev, "ndbus%d", nvdimm_bus->id); rc = device_register(&nvdimm_bus->dev); if (rc) { @@ -984,8 +985,8 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, if (cmd == ND_CMD_CALL) { func = pkg.nd_command; - dev_dbg(dev, "%s:%s, idx: %llu, in: %u, out: %u, len %llu\n", - __func__, dimm_name, pkg.nd_command, + dev_dbg(dev, "%s, idx: %llu, in: %u, out: %u, len %llu\n", + dimm_name, pkg.nd_command, in_len, out_len, buf_len); } @@ -996,8 +997,8 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, u32 copy; if (out_size == UINT_MAX) { - dev_dbg(dev, "%s:%s unknown output size cmd: %s field: %d\n", - __func__, dimm_name, cmd_name, i); + dev_dbg(dev, "%s unknown output size cmd: %s field: %d\n", + dimm_name, cmd_name, i); return -EFAULT; } if (out_len < sizeof(out_env)) @@ -1012,9 +1013,8 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, buf_len = (u64) out_len + (u64) in_len; if (buf_len > ND_IOCTL_MAX_BUFLEN) { - dev_dbg(dev, "%s:%s cmd: %s buf_len: %llu > %d\n", __func__, - dimm_name, cmd_name, buf_len, - ND_IOCTL_MAX_BUFLEN); + dev_dbg(dev, "%s cmd: %s buf_len: %llu > %d\n", dimm_name, + cmd_name, buf_len, ND_IOCTL_MAX_BUFLEN); return -EINVAL; } diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c index b2fc29b8279b..30852270484f 100644 --- a/drivers/nvdimm/claim.c +++ b/drivers/nvdimm/claim.c @@ -148,7 +148,7 @@ ssize_t nd_namespace_store(struct device *dev, char *name; if (dev->driver) { - dev_dbg(dev, "%s: -EBUSY\n", __func__); + dev_dbg(dev, "namespace already active\n"); return -EBUSY; } diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 1dc527660637..acce050856a8 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -134,7 +134,7 @@ static void nvdimm_map_release(struct kref *kref) nvdimm_map = container_of(kref, struct nvdimm_map, kref); nvdimm_bus = nvdimm_map->nvdimm_bus; - dev_dbg(&nvdimm_bus->dev, "%s: %pa\n", __func__, &nvdimm_map->offset); + dev_dbg(&nvdimm_bus->dev, "%pa\n", &nvdimm_map->offset); list_del(&nvdimm_map->list); if (nvdimm_map->flags) memunmap(nvdimm_map->mem); @@ -230,8 +230,8 @@ static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf, for (i = 0; i < 16; i++) { if (!isxdigit(str[0]) || !isxdigit(str[1])) { - dev_dbg(dev, "%s: pos: %d buf[%zd]: %c buf[%zd]: %c\n", - __func__, i, str - buf, str[0], + dev_dbg(dev, "pos: %d buf[%zd]: %c buf[%zd]: %c\n", + i, str - buf, str[0], str + 1 - buf, str[1]); return -EINVAL; } diff --git a/drivers/nvdimm/dax_devs.c b/drivers/nvdimm/dax_devs.c index 1bf2bd318371..0453f49dc708 100644 --- a/drivers/nvdimm/dax_devs.c +++ b/drivers/nvdimm/dax_devs.c @@ -24,7 +24,7 @@ static void nd_dax_release(struct device *dev) struct nd_dax *nd_dax = to_nd_dax(dev); struct nd_pfn *nd_pfn = &nd_dax->nd_pfn; - dev_dbg(dev, "%s\n", __func__); + dev_dbg(dev, "trace\n"); nd_detach_ndns(dev, &nd_pfn->ndns); ida_simple_remove(&nd_region->dax_ida, nd_pfn->id); kfree(nd_pfn->uuid); @@ -129,8 +129,7 @@ int nd_dax_probe(struct device *dev, struct nd_namespace_common *ndns) pfn_sb = devm_kzalloc(dev, sizeof(*pfn_sb), GFP_KERNEL); nd_pfn->pfn_sb = pfn_sb; rc = nd_pfn_validate(nd_pfn, DAX_SIG); - dev_dbg(dev, "%s: dax: %s\n", __func__, - rc == 0 ? dev_name(dax_dev) : "<none>"); + dev_dbg(dev, "dax: %s\n", rc == 0 ? dev_name(dax_dev) : "<none>"); if (rc < 0) { nd_detach_ndns(dax_dev, &nd_pfn->ndns); put_device(dax_dev); diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c index f8913b8124b6..233907889f96 100644 --- a/drivers/nvdimm/dimm.c +++ b/drivers/nvdimm/dimm.c @@ -67,9 +67,11 @@ static int nvdimm_probe(struct device *dev) ndd->ns_next = nd_label_next_nsindex(ndd->ns_current); nd_label_copy(ndd, to_next_namespace_index(ndd), to_current_namespace_index(ndd)); - rc = nd_label_reserve_dpa(ndd); - if (ndd->ns_current >= 0) - nvdimm_set_aliasing(dev); + if (ndd->ns_current >= 0) { + rc = nd_label_reserve_dpa(ndd); + if (rc == 0) + nvdimm_set_aliasing(dev); + } nvdimm_clear_locked(dev); nvdimm_bus_unlock(dev); diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 097794d9f786..e00d45522b80 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -131,7 +131,7 @@ int nvdimm_init_config_data(struct nvdimm_drvdata *ndd) } memcpy(ndd->data + offset, cmd->out_buf, cmd->in_length); } - dev_dbg(ndd->dev, "%s: len: %zu rc: %d\n", __func__, offset, rc); + dev_dbg(ndd->dev, "len: %zu rc: %d\n", offset, rc); kfree(cmd); return rc; @@ -266,8 +266,7 @@ void nvdimm_drvdata_release(struct kref *kref) struct device *dev = ndd->dev; struct resource *res, *_r; - dev_dbg(dev, "%s\n", __func__); - + dev_dbg(dev, "trace\n"); nvdimm_bus_lock(dev); for_each_dpa_resource_safe(ndd, res, _r) nvdimm_free_dpa(ndd, res); @@ -660,7 +659,7 @@ int nvdimm_bus_check_dimm_count(struct nvdimm_bus *nvdimm_bus, int dimm_count) nd_synchronize(); device_for_each_child(&nvdimm_bus->dev, &count, count_dimms); - dev_dbg(&nvdimm_bus->dev, "%s: count: %d\n", __func__, count); + dev_dbg(&nvdimm_bus->dev, "count: %d\n", count); if (count != dimm_count) return -ENXIO; return 0; diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c index de66c02f6140..1d28cd656536 100644 --- a/drivers/nvdimm/label.c +++ b/drivers/nvdimm/label.c @@ -45,9 +45,27 @@ unsigned sizeof_namespace_label(struct nvdimm_drvdata *ndd) return ndd->nslabel_size; } +static size_t __sizeof_namespace_index(u32 nslot) +{ + return ALIGN(sizeof(struct nd_namespace_index) + DIV_ROUND_UP(nslot, 8), + NSINDEX_ALIGN); +} + +static int __nvdimm_num_label_slots(struct nvdimm_drvdata *ndd, + size_t index_size) +{ + return (ndd->nsarea.config_size - index_size * 2) / + sizeof_namespace_label(ndd); +} + int nvdimm_num_label_slots(struct nvdimm_drvdata *ndd) { - return ndd->nsarea.config_size / (sizeof_namespace_label(ndd) + 1); + u32 tmp_nslot, n; + + tmp_nslot = ndd->nsarea.config_size / sizeof_namespace_label(ndd); + n = __sizeof_namespace_index(tmp_nslot) / NSINDEX_ALIGN; + + return __nvdimm_num_label_slots(ndd, NSINDEX_ALIGN * n); } size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd) @@ -55,18 +73,14 @@ size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd) u32 nslot, space, size; /* - * The minimum index space is 512 bytes, with that amount of - * index we can describe ~1400 labels which is less than a byte - * of overhead per label. Round up to a byte of overhead per - * label and determine the size of the index region. Yes, this - * starts to waste space at larger config_sizes, but it's - * unlikely we'll ever see anything but 128K. + * Per UEFI 2.7, the minimum size of the Label Storage Area is large + * enough to hold 2 index blocks and 2 labels. The minimum index + * block size is 256 bytes, and the minimum label size is 256 bytes. */ nslot = nvdimm_num_label_slots(ndd); space = ndd->nsarea.config_size - nslot * sizeof_namespace_label(ndd); - size = ALIGN(sizeof(struct nd_namespace_index) + DIV_ROUND_UP(nslot, 8), - NSINDEX_ALIGN) * 2; - if (size <= space) + size = __sizeof_namespace_index(nslot) * 2; + if (size <= space && nslot >= 2) return size / 2; dev_err(ndd->dev, "label area (%d) too small to host (%d byte) labels\n", @@ -121,8 +135,7 @@ static int __nd_label_validate(struct nvdimm_drvdata *ndd) memcpy(sig, nsindex[i]->sig, NSINDEX_SIG_LEN); if (memcmp(sig, NSINDEX_SIGNATURE, NSINDEX_SIG_LEN) != 0) { - dev_dbg(dev, "%s: nsindex%d signature invalid\n", - __func__, i); + dev_dbg(dev, "nsindex%d signature invalid\n", i); continue; } @@ -135,8 +148,8 @@ static int __nd_label_validate(struct nvdimm_drvdata *ndd) labelsize = 128; if (labelsize != sizeof_namespace_label(ndd)) { - dev_dbg(dev, "%s: nsindex%d labelsize %d invalid\n", - __func__, i, nsindex[i]->labelsize); + dev_dbg(dev, "nsindex%d labelsize %d invalid\n", + i, nsindex[i]->labelsize); continue; } @@ -145,30 +158,28 @@ static int __nd_label_validate(struct nvdimm_drvdata *ndd) sum = nd_fletcher64(nsindex[i], sizeof_namespace_index(ndd), 1); nsindex[i]->checksum = __cpu_to_le64(sum_save); if (sum != sum_save) { - dev_dbg(dev, "%s: nsindex%d checksum invalid\n", - __func__, i); + dev_dbg(dev, "nsindex%d checksum invalid\n", i); continue; } seq = __le32_to_cpu(nsindex[i]->seq); if ((seq & NSINDEX_SEQ_MASK) == 0) { - dev_dbg(dev, "%s: nsindex%d sequence: %#x invalid\n", - __func__, i, seq); + dev_dbg(dev, "nsindex%d sequence: %#x invalid\n", i, seq); continue; } /* sanity check the index against expected values */ if (__le64_to_cpu(nsindex[i]->myoff) != i * sizeof_namespace_index(ndd)) { - dev_dbg(dev, "%s: nsindex%d myoff: %#llx invalid\n", - __func__, i, (unsigned long long) + dev_dbg(dev, "nsindex%d myoff: %#llx invalid\n", + i, (unsigned long long) __le64_to_cpu(nsindex[i]->myoff)); continue; } if (__le64_to_cpu(nsindex[i]->otheroff) != (!i) * sizeof_namespace_index(ndd)) { - dev_dbg(dev, "%s: nsindex%d otheroff: %#llx invalid\n", - __func__, i, (unsigned long long) + dev_dbg(dev, "nsindex%d otheroff: %#llx invalid\n", + i, (unsigned long long) __le64_to_cpu(nsindex[i]->otheroff)); continue; } @@ -176,8 +187,7 @@ static int __nd_label_validate(struct nvdimm_drvdata *ndd) size = __le64_to_cpu(nsindex[i]->mysize); if (size > sizeof_namespace_index(ndd) || size < sizeof(struct nd_namespace_index)) { - dev_dbg(dev, "%s: nsindex%d mysize: %#llx invalid\n", - __func__, i, size); + dev_dbg(dev, "nsindex%d mysize: %#llx invalid\n", i, size); continue; } @@ -185,9 +195,8 @@ static int __nd_label_validate(struct nvdimm_drvdata *ndd) if (nslot * sizeof_namespace_label(ndd) + 2 * sizeof_namespace_index(ndd) > ndd->nsarea.config_size) { - dev_dbg(dev, "%s: nsindex%d nslot: %u invalid, config_size: %#x\n", - __func__, i, nslot, - ndd->nsarea.config_size); + dev_dbg(dev, "nsindex%d nslot: %u invalid, config_size: %#x\n", + i, nslot, ndd->nsarea.config_size); continue; } valid[i] = true; @@ -356,8 +365,8 @@ static bool slot_valid(struct nvdimm_drvdata *ndd, sum = nd_fletcher64(nd_label, sizeof_namespace_label(ndd), 1); nd_label->checksum = __cpu_to_le64(sum_save); if (sum != sum_save) { - dev_dbg(ndd->dev, "%s fail checksum. slot: %d expect: %#llx\n", - __func__, slot, sum); + dev_dbg(ndd->dev, "fail checksum. slot: %d expect: %#llx\n", + slot, sum); return false; } } @@ -422,8 +431,8 @@ int nd_label_active_count(struct nvdimm_drvdata *ndd) u64 dpa = __le64_to_cpu(nd_label->dpa); dev_dbg(ndd->dev, - "%s: slot%d invalid slot: %d dpa: %llx size: %llx\n", - __func__, slot, label_slot, dpa, size); + "slot%d invalid slot: %d dpa: %llx size: %llx\n", + slot, label_slot, dpa, size); continue; } count++; @@ -650,7 +659,7 @@ static int __pmem_label_update(struct nd_region *nd_region, slot = nd_label_alloc_slot(ndd); if (slot == UINT_MAX) return -ENXIO; - dev_dbg(ndd->dev, "%s: allocated: %d\n", __func__, slot); + dev_dbg(ndd->dev, "allocated: %d\n", slot); nd_label = to_label(ndd, slot); memset(nd_label, 0, sizeof_namespace_label(ndd)); @@ -678,7 +687,7 @@ static int __pmem_label_update(struct nd_region *nd_region, sum = nd_fletcher64(nd_label, sizeof_namespace_label(ndd), 1); nd_label->checksum = __cpu_to_le64(sum); } - nd_dbg_dpa(nd_region, ndd, res, "%s\n", __func__); + nd_dbg_dpa(nd_region, ndd, res, "\n"); /* update label */ offset = nd_label_offset(ndd, nd_label); @@ -700,7 +709,7 @@ static int __pmem_label_update(struct nd_region *nd_region, break; } if (victim) { - dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot); + dev_dbg(ndd->dev, "free: %d\n", slot); slot = to_slot(ndd, victim->label); nd_label_free_slot(ndd, slot); victim->label = NULL; @@ -868,7 +877,7 @@ static int __blk_label_update(struct nd_region *nd_region, slot = nd_label_alloc_slot(ndd); if (slot == UINT_MAX) goto abort; - dev_dbg(ndd->dev, "%s: allocated: %d\n", __func__, slot); + dev_dbg(ndd->dev, "allocated: %d\n", slot); nd_label = to_label(ndd, slot); memset(nd_label, 0, sizeof_namespace_label(ndd)); @@ -928,7 +937,7 @@ static int __blk_label_update(struct nd_region *nd_region, /* free up now unused slots in the new index */ for_each_set_bit(slot, victim_map, victim_map ? nslot : 0) { - dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot); + dev_dbg(ndd->dev, "free: %d\n", slot); nd_label_free_slot(ndd, slot); } @@ -1092,7 +1101,7 @@ static int del_labels(struct nd_mapping *nd_mapping, u8 *uuid) active--; slot = to_slot(ndd, nd_label); nd_label_free_slot(ndd, slot); - dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot); + dev_dbg(ndd->dev, "free: %d\n", slot); list_move_tail(&label_ent->list, &list); label_ent->label = NULL; } @@ -1100,7 +1109,7 @@ static int del_labels(struct nd_mapping *nd_mapping, u8 *uuid) if (active == 0) { nd_mapping_free_labels(nd_mapping); - dev_dbg(ndd->dev, "%s: no more active labels\n", __func__); + dev_dbg(ndd->dev, "no more active labels\n"); } mutex_unlock(&nd_mapping->lock); diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h index 1ebf4d3d01ba..18bbe183b3a9 100644 --- a/drivers/nvdimm/label.h +++ b/drivers/nvdimm/label.h @@ -33,7 +33,7 @@ enum { BTTINFO_UUID_LEN = 16, BTTINFO_FLAG_ERROR = 0x1, /* error state (read-only) */ BTTINFO_MAJOR_VERSION = 1, - ND_LABEL_MIN_SIZE = 512 * 129, /* see sizeof_namespace_index() */ + ND_LABEL_MIN_SIZE = 256 * 4, /* see sizeof_namespace_index() */ ND_LABEL_ID_SIZE = 50, ND_NSINDEX_INIT = 0x1, }; diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 658ada497be0..28afdd668905 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -421,7 +421,7 @@ static ssize_t alt_name_store(struct device *dev, rc = __alt_name_store(dev, buf, len); if (rc >= 0) rc = nd_namespace_label_update(nd_region, dev); - dev_dbg(dev, "%s: %s(%zd)\n", __func__, rc < 0 ? "fail " : "", rc); + dev_dbg(dev, "%s(%zd)\n", rc < 0 ? "fail " : "", rc); nvdimm_bus_unlock(dev); device_unlock(dev); @@ -1007,7 +1007,7 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) if (uuid_not_set(uuid, dev, __func__)) return -ENXIO; if (nd_region->ndr_mappings == 0) { - dev_dbg(dev, "%s: not associated with dimm(s)\n", __func__); + dev_dbg(dev, "not associated with dimm(s)\n"); return -ENXIO; } @@ -1105,8 +1105,7 @@ static ssize_t size_store(struct device *dev, *uuid = NULL; } - dev_dbg(dev, "%s: %llx %s (%d)\n", __func__, val, rc < 0 - ? "fail" : "success", rc); + dev_dbg(dev, "%llx %s (%d)\n", val, rc < 0 ? "fail" : "success", rc); nvdimm_bus_unlock(dev); device_unlock(dev); @@ -1270,8 +1269,8 @@ static ssize_t uuid_store(struct device *dev, rc = nd_namespace_label_update(nd_region, dev); else kfree(uuid); - dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__, - rc, buf, buf[len - 1] == '\n' ? "" : "\n"); + dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, + buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); device_unlock(dev); @@ -1355,9 +1354,8 @@ static ssize_t sector_size_store(struct device *dev, rc = nd_size_select_store(dev, buf, lbasize, supported); if (rc >= 0) rc = nd_namespace_label_update(nd_region, dev); - dev_dbg(dev, "%s: result: %zd %s: %s%s", __func__, - rc, rc < 0 ? "tried" : "wrote", buf, - buf[len - 1] == '\n' ? "" : "\n"); + dev_dbg(dev, "result: %zd %s: %s%s", rc, rc < 0 ? "tried" : "wrote", + buf, buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); device_unlock(dev); @@ -1519,7 +1517,7 @@ static ssize_t holder_class_store(struct device *dev, rc = __holder_class_store(dev, buf); if (rc >= 0) rc = nd_namespace_label_update(nd_region, dev); - dev_dbg(dev, "%s: %s(%zd)\n", __func__, rc < 0 ? "fail " : "", rc); + dev_dbg(dev, "%s(%zd)\n", rc < 0 ? "fail " : "", rc); nvdimm_bus_unlock(dev); device_unlock(dev); @@ -1717,8 +1715,7 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev) if (uuid_not_set(nsblk->uuid, &ndns->dev, __func__)) return ERR_PTR(-ENODEV); if (!nsblk->lbasize) { - dev_dbg(&ndns->dev, "%s: sector size not set\n", - __func__); + dev_dbg(&ndns->dev, "sector size not set\n"); return ERR_PTR(-ENODEV); } if (!nd_namespace_blk_validate(nsblk)) @@ -1798,9 +1795,7 @@ static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid, } if (found_uuid) { - dev_dbg(ndd->dev, - "%s duplicate entry for uuid\n", - __func__); + dev_dbg(ndd->dev, "duplicate entry for uuid\n"); return false; } found_uuid = true; @@ -1926,7 +1921,7 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, } if (i < nd_region->ndr_mappings) { - struct nvdimm_drvdata *ndd = to_ndd(&nd_region->mapping[i]); + struct nvdimm *nvdimm = nd_region->mapping[i].nvdimm; /* * Give up if we don't find an instance of a uuid at each @@ -1934,7 +1929,7 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, * find a dimm with two instances of the same uuid. */ dev_err(&nd_region->dev, "%s missing label for %pUb\n", - dev_name(ndd->dev), nd_label->uuid); + nvdimm_name(nvdimm), nd_label->uuid); rc = -EINVAL; goto err; } @@ -1994,14 +1989,13 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, namespace_pmem_release(dev); switch (rc) { case -EINVAL: - dev_dbg(&nd_region->dev, "%s: invalid label(s)\n", __func__); + dev_dbg(&nd_region->dev, "invalid label(s)\n"); break; case -ENODEV: - dev_dbg(&nd_region->dev, "%s: label not found\n", __func__); + dev_dbg(&nd_region->dev, "label not found\n"); break; default: - dev_dbg(&nd_region->dev, "%s: unexpected err: %d\n", - __func__, rc); + dev_dbg(&nd_region->dev, "unexpected err: %d\n", rc); break; } return ERR_PTR(rc); @@ -2334,8 +2328,8 @@ static struct device **scan_labels(struct nd_region *nd_region) } - dev_dbg(&nd_region->dev, "%s: discovered %d %s namespace%s\n", - __func__, count, is_nd_blk(&nd_region->dev) + dev_dbg(&nd_region->dev, "discovered %d %s namespace%s\n", + count, is_nd_blk(&nd_region->dev) ? "blk" : "pmem", count == 1 ? "" : "s"); if (count == 0) { @@ -2467,7 +2461,7 @@ static int init_active_labels(struct nd_region *nd_region) get_ndd(ndd); count = nd_label_active_count(ndd); - dev_dbg(ndd->dev, "%s: %d\n", __func__, count); + dev_dbg(ndd->dev, "count: %d\n", count); if (!count) continue; for (j = 0; j < count; j++) { diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 8d6375ee0fda..9dad5d737309 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -341,7 +341,6 @@ static inline struct device *nd_dax_create(struct nd_region *nd_region) } #endif -struct nd_region *to_nd_region(struct device *dev); int nd_region_to_nstype(struct nd_region *nd_region); int nd_region_register_namespaces(struct nd_region *nd_region, int *err); u64 nd_region_interleave_set_cookie(struct nd_region *nd_region, diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c new file mode 100644 index 000000000000..85013bad35de --- /dev/null +++ b/drivers/nvdimm/of_pmem.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#define pr_fmt(fmt) "of_pmem: " fmt + +#include <linux/of_platform.h> +#include <linux/of_address.h> +#include <linux/libnvdimm.h> +#include <linux/module.h> +#include <linux/ioport.h> +#include <linux/slab.h> + +static const struct attribute_group *region_attr_groups[] = { + &nd_region_attribute_group, + &nd_device_attribute_group, + NULL, +}; + +static const struct attribute_group *bus_attr_groups[] = { + &nvdimm_bus_attribute_group, + NULL, +}; + +struct of_pmem_private { + struct nvdimm_bus_descriptor bus_desc; + struct nvdimm_bus *bus; +}; + +static int of_pmem_region_probe(struct platform_device *pdev) +{ + struct of_pmem_private *priv; + struct device_node *np; + struct nvdimm_bus *bus; + bool is_volatile; + int i; + + np = dev_of_node(&pdev->dev); + if (!np) + return -ENXIO; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->bus_desc.attr_groups = bus_attr_groups; + priv->bus_desc.provider_name = "of_pmem"; + priv->bus_desc.module = THIS_MODULE; + priv->bus_desc.of_node = np; + + priv->bus = bus = nvdimm_bus_register(&pdev->dev, &priv->bus_desc); + if (!bus) { + kfree(priv); + return -ENODEV; + } + platform_set_drvdata(pdev, priv); + + is_volatile = !!of_find_property(np, "volatile", NULL); + dev_dbg(&pdev->dev, "Registering %s regions from %pOF\n", + is_volatile ? "volatile" : "non-volatile", np); + + for (i = 0; i < pdev->num_resources; i++) { + struct nd_region_desc ndr_desc; + struct nd_region *region; + + /* + * NB: libnvdimm copies the data from ndr_desc into it's own + * structures so passing a stack pointer is fine. + */ + memset(&ndr_desc, 0, sizeof(ndr_desc)); + ndr_desc.attr_groups = region_attr_groups; + ndr_desc.numa_node = of_node_to_nid(np); + ndr_desc.res = &pdev->resource[i]; + ndr_desc.of_node = np; + set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags); + + if (is_volatile) + region = nvdimm_volatile_region_create(bus, &ndr_desc); + else + region = nvdimm_pmem_region_create(bus, &ndr_desc); + + if (!region) + dev_warn(&pdev->dev, "Unable to register region %pR from %pOF\n", + ndr_desc.res, np); + else + dev_dbg(&pdev->dev, "Registered region %pR from %pOF\n", + ndr_desc.res, np); + } + + return 0; +} + +static int of_pmem_region_remove(struct platform_device *pdev) +{ + struct of_pmem_private *priv = platform_get_drvdata(pdev); + + nvdimm_bus_unregister(priv->bus); + kfree(priv); + + return 0; +} + +static const struct of_device_id of_pmem_region_match[] = { + { .compatible = "pmem-region" }, + { }, +}; + +static struct platform_driver of_pmem_region_driver = { + .probe = of_pmem_region_probe, + .remove = of_pmem_region_remove, + .driver = { + .name = "of_pmem", + .owner = THIS_MODULE, + .of_match_table = of_pmem_region_match, + }, +}; + +module_platform_driver(of_pmem_region_driver); +MODULE_DEVICE_TABLE(of, of_pmem_region_match); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("IBM Corporation"); diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index 2f4d18752c97..30b08791597d 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -27,7 +27,7 @@ static void nd_pfn_release(struct device *dev) struct nd_region *nd_region = to_nd_region(dev->parent); struct nd_pfn *nd_pfn = to_nd_pfn(dev); - dev_dbg(dev, "%s\n", __func__); + dev_dbg(dev, "trace\n"); nd_detach_ndns(&nd_pfn->dev, &nd_pfn->ndns); ida_simple_remove(&nd_region->pfn_ida, nd_pfn->id); kfree(nd_pfn->uuid); @@ -94,8 +94,8 @@ static ssize_t mode_store(struct device *dev, else rc = -EINVAL; } - dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__, - rc, buf, buf[len - 1] == '\n' ? "" : "\n"); + dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, + buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); device_unlock(dev); @@ -144,8 +144,8 @@ static ssize_t align_store(struct device *dev, nvdimm_bus_lock(dev); rc = nd_size_select_store(dev, buf, &nd_pfn->align, nd_pfn_supported_alignments()); - dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__, - rc, buf, buf[len - 1] == '\n' ? "" : "\n"); + dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, + buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); device_unlock(dev); @@ -171,8 +171,8 @@ static ssize_t uuid_store(struct device *dev, device_lock(dev); rc = nd_uuid_store(dev, &nd_pfn->uuid, buf, len); - dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__, - rc, buf, buf[len - 1] == '\n' ? "" : "\n"); + dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, + buf[len - 1] == '\n' ? "" : "\n"); device_unlock(dev); return rc ? rc : len; @@ -201,8 +201,8 @@ static ssize_t namespace_store(struct device *dev, device_lock(dev); nvdimm_bus_lock(dev); rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len); - dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__, - rc, buf, buf[len - 1] == '\n' ? "" : "\n"); + dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf, + buf[len - 1] == '\n' ? "" : "\n"); nvdimm_bus_unlock(dev); device_unlock(dev); @@ -314,8 +314,8 @@ struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn, dev = &nd_pfn->dev; device_initialize(&nd_pfn->dev); if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) { - dev_dbg(&ndns->dev, "%s failed, already claimed by %s\n", - __func__, dev_name(ndns->claim)); + dev_dbg(&ndns->dev, "failed, already claimed by %s\n", + dev_name(ndns->claim)); put_device(dev); return NULL; } @@ -510,8 +510,7 @@ int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns) nd_pfn = to_nd_pfn(pfn_dev); nd_pfn->pfn_sb = pfn_sb; rc = nd_pfn_validate(nd_pfn, PFN_SIG); - dev_dbg(dev, "%s: pfn: %s\n", __func__, - rc == 0 ? dev_name(pfn_dev) : "<none>"); + dev_dbg(dev, "pfn: %s\n", rc == 0 ? dev_name(pfn_dev) : "<none>"); if (rc < 0) { nd_detach_ndns(pfn_dev, &nd_pfn->ndns); put_device(pfn_dev); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 06f8dcc52ca6..85dfb3dc3981 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -66,7 +66,7 @@ static blk_status_t pmem_clear_poison(struct pmem_device *pmem, rc = BLK_STS_IOERR; if (cleared > 0 && cleared / 512) { cleared /= 512; - dev_dbg(dev, "%s: %#llx clear %ld sector%s\n", __func__, + dev_dbg(dev, "%#llx clear %ld sector%s\n", (unsigned long long) sector, cleared, cleared > 1 ? "s" : ""); badblocks_clear(&pmem->bb, sector, cleared); @@ -547,17 +547,7 @@ static struct nd_device_driver nd_pmem_driver = { .type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM, }; -static int __init pmem_init(void) -{ - return nd_driver_register(&nd_pmem_driver); -} -module_init(pmem_init); - -static void pmem_exit(void) -{ - driver_unregister(&nd_pmem_driver.drv); -} -module_exit(pmem_exit); +module_nd_driver(nd_pmem_driver); MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/nvdimm/region.c b/drivers/nvdimm/region.c index 034f0a07d627..b9ca0033cc99 100644 --- a/drivers/nvdimm/region.c +++ b/drivers/nvdimm/region.c @@ -27,10 +27,10 @@ static int nd_region_probe(struct device *dev) if (nd_region->num_lanes > num_online_cpus() && nd_region->num_lanes < num_possible_cpus() && !test_and_set_bit(0, &once)) { - dev_info(dev, "online cpus (%d) < concurrent i/o lanes (%d) < possible cpus (%d)\n", + dev_dbg(dev, "online cpus (%d) < concurrent i/o lanes (%d) < possible cpus (%d)\n", num_online_cpus(), nd_region->num_lanes, num_possible_cpus()); - dev_info(dev, "setting nr_cpus=%d may yield better libnvdimm device performance\n", + dev_dbg(dev, "setting nr_cpus=%d may yield better libnvdimm device performance\n", nd_region->num_lanes); } diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 1593e1806b16..a612be6f019d 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -182,6 +182,14 @@ struct nd_region *to_nd_region(struct device *dev) } EXPORT_SYMBOL_GPL(to_nd_region); +struct device *nd_region_dev(struct nd_region *nd_region) +{ + if (!nd_region) + return NULL; + return &nd_region->dev; +} +EXPORT_SYMBOL_GPL(nd_region_dev); + struct nd_blk_region *to_nd_blk_region(struct device *dev) { struct nd_region *nd_region = to_nd_region(dev); @@ -1014,6 +1022,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, dev->parent = &nvdimm_bus->dev; dev->type = dev_type; dev->groups = ndr_desc->attr_groups; + dev->of_node = ndr_desc->of_node; nd_region->ndr_size = resource_size(ndr_desc->res); nd_region->ndr_start = ndr_desc->res->start; nd_device_register(dev); |